CN114710688B - Live broadcast interaction system and method capable of being configured to automatically drive virtual anchor - Google Patents
Live broadcast interaction system and method capable of being configured to automatically drive virtual anchor Download PDFInfo
- Publication number
- CN114710688B CN114710688B CN202210303776.5A CN202210303776A CN114710688B CN 114710688 B CN114710688 B CN 114710688B CN 202210303776 A CN202210303776 A CN 202210303776A CN 114710688 B CN114710688 B CN 114710688B
- Authority
- CN
- China
- Prior art keywords
- live
- server
- client
- bullet screen
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 title claims description 16
- 238000007726 management method Methods 0.000 claims description 18
- 230000009471 action Effects 0.000 claims description 13
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 10
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 claims description 9
- 239000003795 chemical substances by application Substances 0.000 claims description 9
- 229910052711 selenium Inorganic materials 0.000 claims description 9
- 239000011669 selenium Substances 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 210000001503 joint Anatomy 0.000 claims description 2
- 230000008569 process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241000282376 Panthera tigris Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010367 cloning Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004091 panning Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000135 prohibitive effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/70—Software maintenance or management
- G06F8/71—Version control; Configuration management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2542—Management at additional data server, e.g. shopping server, rights management server for selling goods, e.g. TV shopping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/426—Internal components of the client ; Characteristics thereof
- H04N21/42653—Internal components of the client ; Characteristics thereof for processing graphics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4884—Data services, e.g. news ticker for displaying subtitles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
- H04N21/643—Communication protocols
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Social Psychology (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computer Graphics (AREA)
- Computer Security & Cryptography (AREA)
- Computational Linguistics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to a configurable live interaction system for automatically driving a virtual anchor, which comprises a client, a FAQ server, a voice server, a barrage acquisition service unit, a Unity3D virtual animation service unit and a user management server, wherein the user management server is used for managing the live interaction system; the client is respectively connected with the bullet screen acquisition service unit, the Unity3D virtual animation service unit and the user management server; and the user management server is respectively connected with the FAQ server and the voice server. The invention effectively reduces the labor cost in live selling of the E-commerce and enables the virtual anchor to support the configurable automatic flow.
Description
Technical Field
The invention relates to the technical field of computer software, in particular to a live broadcast interaction system and method capable of being configured and automatically driven to a virtual anchor.
Background
In the live selling process of the electronic commerce, the situation of the commodity is usually introduced manually, then interaction with visitors is carried out at intervals, the introduced commodity is often some introduction books prepared in advance, and FAQ related to the commodity is possibly aimed at, so that a live host can interact with vermicelli relatively accurately in the live broadcasting process. However, repetitive work makes labor costs prohibitive, and thus requires a series of repetitive, procedural works to be handled by the program, taking into account the enablement of the intelligent virtual anchor. On the one hand, the user can combine the self commodity to modify the table book and FAQ data when using the programmed virtual anchor, and on the other hand, the user can provide necessary assistance on the interaction, such as timely welcome, answering and the gift, and the like. The technical difficulties are mainly that the flow configuration and the adaptation to different live broadcast platforms are realized, and particularly how to establish efficient and intelligent drive virtual live broadcast interaction is also required to be simulated and formulated.
Disclosure of Invention
In view of the above, the present invention aims to provide a live interaction system and method for configurable automation driving virtual anchor, which is implemented to enable virtual anchor and support configurable automation flow.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a configurable automation driven virtual anchor live broadcast interactive system comprises a client, a FAQ server, a voice server, a barrage acquisition service unit, a Unity3D virtual animation service unit and a user management server; the client is respectively connected with the bullet screen acquisition service unit, the Unity3D virtual animation service unit and the user management server; and the user management server is respectively connected with the FAQ server and the voice server.
Further, the client implements configurable input, including: scene animation selection, table book selection editing, welcome and answer template customization, FAQ editing, synthesized sound selection, material uploading and running log.
Furthermore, the FAQ server pre-transfers sentence-level vectors to a question-answer library uploaded by a user based on a word vector model of direct Skip-Gram large-scale unsupervised learning.
Furthermore, the Unity3D virtual animation service unit designs virtual anchor in advance in different forms, configures different action combinations for each virtual anchor, monitors through an opening interface, realizes the butt joint with a client, and controls the request sound action output by the client.
An interaction method of a live interaction system capable of being configured to automatically drive a virtual anchor comprises the following steps:
the client configures a virtual anchor workflow to be driven;
when the client starts live broadcasting after configuration is completed and enters a vermicelli question and answer, the latest n number of barrages are extracted, and FAQ calculation requests are carried out after n numbers are filtered, wherein n is set by a user;
the bullet screen collecting stage adopts two ways to collect, including bullet screen collection based on the protobuf format of http transmission and bullet screen collection based on the protobuf format of websocket transmission.
Further, the method comprises extracting the latest n number of barrages, specifically, setting the initialization time to be T 0 =0, and the current time is T m M represents the number of times the workflow enters a vermicelli question and answer, if T m >T 0 And the current time for sending the bullet screen of the vermicelli is in the interval [ T ] 0 ,T m ]The generated barrage is used as a standby candidate set 0 To further extract valid set of interaction data from the candidate set 1 Then judging the proportion of each Chinese character>=0.9, and the alphanumerics<5, other characters<4.
Further, the FAQ calculation specifically includes: if the interactive data set is set 1 One of the existing words W m If the character is not in the semantic word set, the character differential editing distance is used as a similarity spam calculation;
requesting FAQ return contains highest similarity pairing problem Q m Corresponding interactive text answer A m By parsing the answer A m Matching the action group set preset by the user, and the client side will A m And requesting a voice synthesis server, transmitting the returned voice and the action set to the Unity3D virtual animation service, and finally pushing the synthesized video stream to the live broadcasting room.
Further, the bullet screen acquisition of the protobuf format based on http transmission specifically comprises the following steps:
(1) Inputting a live broadcast page address to be acquired;
(2) Using a selenium tool to drive a browser to open a live broadcast page, and analyzing the page to acquire information such as a required live broadcast room id;
(3) Starting a local agent tool, configuring a tool script, and collecting data from a designated live broadcasting room id;
(4) Configuring a local agent address and a port by using a selenium tool, driving a browser to open a live page to be acquired and keeping the page resident in the background;
(5) The local agent tool starts to capture the interface path conforming to the specified rule and stores the interface return data to the local directory;
(6) Monitoring a specified local directory, and analyzing the stored protobuf format data in real time;
(7) And storing the bullet screen information after analysis to a designated position.
Further, the bullet screen collection of the protobuf format based on websocket transmission specifically comprises the following steps:
(1) Inputting a live broadcast page address to be acquired;
(2) Using a selenium tool to drive a browser to open a live page, and obtaining html source codes of the page;
(3) Analyzing bullet screen websocket addresses, live stream ids and check token information from html source codes;
(4) Acquiring the latest mapping file of the gift id and the name of the live broadcasting room, analyzing and recording the mapping file into a memory;
(5) Simulating a webpage request to interact with a websocket interface of the server by using an aiohttp framework, and analyzing returned data of the server;
(6) And storing the bullet screen information after analysis to a designated position.
Furthermore, the client is also provided with a user tracking management mechanism, a user use tracking function is added, any user can receive and send messages with the user management server when using the related function service of the client, and the system can copy and store various operation information of the user and then analyze the operation information through an auxiliary analysis tool.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention effectively reduces the labor cost in live selling of the E-commerce and enables the virtual anchor to support the configurable automatic flow.
2. The system user can quickly set up own virtual anchor without professional live interaction capability, and can save time to concentrate on scenario table interaction text preparation and optimization on improving the conversion rate of live sales.
3. The independent personalized customizable FAQ data management server is convenient for data backup and extraction, is used for analyzing the difference of FAQs among different users, improves the personalized FAQ data customization, reduces redundancy, improves the accuracy of semantic similarity, and further improves the correlation with vermicelli interaction.
4. The invention can privately configure the voice synthesis service, besides providing different existing offline voice synthesis packages, the user can upload a clear speaking audio segment, provide the voice cloning service, create the differential sound ray voice effect and realize the customization of privately-configured voice.
Drawings
Fig. 1 is a diagram of a system framework of the present invention.
Detailed Description
The invention will be further described with reference to the accompanying drawings and examples.
Referring to fig. 1, the invention provides a live interaction system capable of configuring an automation driving virtual anchor, which comprises a client, a FAQ server, a voice server, a barrage acquisition service unit, a Unity3D virtual animation service unit and a user management server; the client is respectively connected with the bullet screen acquisition service unit, the Unity3D virtual animation service unit and the user management server; and the user management server is respectively connected with the FAQ server and the voice server.
In this embodiment, the client implements configurable input, including: scene animation selection, table book selection editing, welcome and answer template customization, FAQ editing, synthesized sound selection, material uploading and running log.
In this embodiment, the voice server synthesizes voice for the text requested by the client, interfaces the offline voice synthesis package, and provides different sound rays for the user to select.
In this embodiment, the FAQ server pre-converts sentence-level vectors to question-answer libraries uploaded by the user based on a word vector model for direct Skip-Gram large-scale unsupervised learning.
In this embodiment, the Unity3D virtual animation service unit designs virtual anchor in advance in different forms, configures different action combinations for each virtual anchor, monitors through an open interface, realizes the interface with the client, and controls the request sound action output by the client.
In this embodiment, the bullet screen acquisition service unit acquires bullet screen information of the live broadcasting room through the network streaming packet, and the client program controls and extracts useful information to be interacted.
In this embodiment, the user management server is used to perform identity authentication and management on the user, and track and feedback the usage situation.
In this embodiment, an interaction method of a live interaction system capable of being configured to automatically drive a virtual anchor is further provided, including the following steps:
configuration preview stage:
the client configures a virtual anchor workflow to be driven;
in this embodiment, the workflow includes: "scenario table book-welcome approach-answer gift-atmosphere maintenance-vermicelli question-scenario table book-the first place, the order of the attention links may be custom. The effect of executing the virtual anchor can be previewed for each small section of scenario book, and the adaptive sound and action combination is adjusted; welcome and answer may be custom set up templates, such as welcome templates resembling "welcome user little fairy into direct broadcast room", such as answer templates resembling "thank user gift, atmosphere-! ", user and gift are variables; atmosphere maintenance sets some alternative speech techniques, and can randomly set rules at random or output in a workflow; the vermicelli question and answer is carried out in the live broadcast stage, and the configuration preview stage mainly configures the FAQ text data set in the field. Multiple scenes can be set, each scene has a self-defined virtual anchor workflow, different materials under the scenes can be configured, including a pure single-person mode, a single-material mode and a double-material mode, and once the different scenes are configured, editing can be modified and live broadcasting can be started at any time later.
Live broadcasting stage:
in the live broadcast process, the system can clearly monitor which step the workflow is executed by the user, pause and modify the workflow which is not finished at any time. When the workflow enters the vermicelli question and answer, the latest n number of barrages are extracted, and the FAQ request is carried out after the n number is filtered, wherein n is set by a user and the default value is 10. The invention is embodied in that the time of initialization is assumed to be T 0 =0, and the current time is T m M represents the number of times the workflow enters a vermicelli question and answer, if T m >T 0 And the current time for sending the bullet screen of the vermicelli is in the interval [ T ] 0 ,T m ]The generated barrage is used as a standby candidate set 0 To further extract valid set of interaction data from the candidate set 1 Then judging the proportion of each Chinese character>=0.9, and the alphanumerics<5, other characters<4.
The FAQ calculation comprises two modes, namely, semantic word vector cosine similarity based on direct Skip-Gram large-scale unsupervised learning and similarity calculation based on character differentiation editing distance, and the two similarity calculation modes are fused in consideration of the problem that semantic word vectors possibly have word set defects. In particular, if the set of interactive data is set 1 One of the existing words W m If the similarity is not in the semantic word set, the character differential editing distance is used as the similarity spam calculation. Requesting FAQ return contains highest similarity pairing problem Q m Corresponding interactive text answer A m By parsing the answer A m Matching the action group set preset by the user, and the client side will A m And requesting a voice synthesis server, transmitting the returned voice and the action set to the Unity3D virtual animation service, and finally pushing the synthesized video stream to the live broadcasting room.
Bullet screen acquisition stage:
two effective acquisition technical means are provided, and acquisition of mainstream live broadcasting platforms including panning, sound shaking, fast hand, jindong, nailing, fighting fish, tiger teeth, NOW and the like is realized, and the method is specifically as follows:
the bullet screen acquisition of the protobuf format based on http transmission specifically comprises the following steps:
(1) Inputting a live broadcast page address to be acquired;
(2) Using a selenium tool to drive a browser to open a live broadcast page, and analyzing the page to acquire information such as a required live broadcast room id;
(3) Starting a local agent tool, configuring a tool script, and collecting data from a designated live broadcasting room id;
(4) Configuring a local agent address and a port by using a selenium tool, driving a browser to open a live page to be acquired and keeping the page resident in the background;
(5) The local agent tool starts to capture the interface path conforming to the specified rule and stores the interface return data to the local directory;
(6) Monitoring a specified local directory, and analyzing the stored protobuf format data in real time;
(7) And storing the bullet screen information after analysis to a designated position.
The bullet screen acquisition of the protobuf format based on websocket transmission specifically comprises the following steps:
(1) Inputting a live broadcast page address to be acquired;
(2) Using a selenium tool to drive a browser to open a live page, and obtaining html source codes of the page;
(3) Analyzing bullet screen websocket addresses, live stream ids and check token information from html source codes;
(4) Acquiring the latest mapping file of the gift id and the name of the live broadcasting room, analyzing and recording the mapping file into a memory;
(5) Simulating a webpage request to interact with a websocket interface of the server by using an aiohttp framework, and analyzing returned data of the server;
(6) And storing the bullet screen information after analysis to a designated position.
In this embodiment, preferably, the client is further provided with a user tracking management mechanism, and a user usage tracking function is added, so that any user can receive and send messages with the user management server when using the function service related to the client, and the system can copy and store various operation information of the user, and then analyze the operation information through an auxiliary analysis tool. Through the user tracking management function, if faults occur, faults caused by errors of which link can be rapidly judged.
The foregoing description is only of the preferred embodiments of the invention, and all changes and modifications that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (2)
1. The interactive method of the live broadcast interactive system capable of being configured to automatically drive the virtual anchor is characterized by comprising the live broadcast interactive system capable of being configured to automatically drive the virtual anchor, wherein the live broadcast interactive system capable of being configured to automatically drive the virtual anchor comprises a client, a FAQ server, a voice server, a bullet screen acquisition service unit, a Unity3D virtual animation service unit and a user management server; the client is respectively connected with the bullet screen acquisition service unit, the Unity3D virtual animation service unit and the user management server; the user management server is connected with the FAQ server and the voice server respectively; the client implementing configurable inputs, comprising: scene animation selection, table book selection editing, welcome answer template customization, FAQ editing, synthesized sound selection, material uploading and running log; the FAQ server converts a question-answer library uploaded by a user into a sentence-level vector in advance based on a word vector model of direct Skip-Gram large-scale unsupervised learning; the Unity3D virtual animation service unit designs virtual anchor in different forms in advance, configures different action combinations for each virtual anchor, monitors through an opening interface, realizes the butt joint with a client, and controls the request sound action output by the client;
a live interaction method capable of configuring an automation driven virtual anchor comprises the following steps:
the client configures a virtual anchor workflow to be driven;
when the client starts live broadcasting after configuration is completed and enters a vermicelli question and answer, the latest n number of barrages are extracted, and FAQ calculation requests are carried out after n numbers are filtered, wherein n is set by a user;
the bullet screen collecting stage adopts two modes to collect, including bullet screen collecting based on the protobuf format of http transmission and bullet screen collecting based on the protobuf format of websocket transmission;
the method comprises extracting n number of barrages, specifically, setting initialization time as T 0 =0, and the current time is T m M represents the number of times the workflow enters a vermicelli question and answer, if T m >T 0 And the current time for sending the bullet screen of the vermicelli is in the interval [ T ] 0 ,T m ]The generated barrage is used as a standby candidate set 0 To further extract valid set of interaction data from the candidate set 1 Then judging the proportion of each Chinese character>=0.9, and the alphanumerics<5, other characters<4;
the FAQ calculation specifically comprises the following steps: if the interactive data set is set 1 One of the existing words W m If the character is not in the semantic word set, the character differential editing distance is used as a similarity spam calculation;
requesting FAQ return contains highest similarity pairing problem Q m Corresponding interactive text answer A m By parsing the answer A m Matching the action group set preset by the user, and the client side will A m Requesting a voice synthesis server, transmitting the returned voice and the action set to a Unity3D virtual animation service, and finally pushing the voice to a live broadcasting room to synthesize a video stream;
the bullet screen acquisition based on the http transmission and in the protobuf format comprises the following steps:
(1) Inputting a live broadcast page address to be acquired;
(2) Using a selenium tool to drive a browser to open a live broadcast page, and analyzing the page to acquire information such as a required live broadcast room id;
(3) Starting a local agent tool, configuring a tool script, and collecting data from a designated live broadcasting room id;
(4) Configuring a local agent address and a port by using a selenium tool, driving a browser to open a live page to be acquired and keeping the page resident in the background;
(5) The local agent tool starts to capture the interface path conforming to the specified rule and stores the interface return data to the local directory;
(6) Monitoring a specified local directory, and analyzing the stored protobuf format data in real time;
(7) Storing the bullet screen information after analysis to a designated position;
the bullet screen acquisition based on the websocket transmission protobuf format specifically comprises the following steps:
(1) Inputting a live broadcast page address to be acquired;
(2) Using a selenium tool to drive a browser to open a live page, and obtaining html source codes of the page;
(3) Analyzing bullet screen websocket addresses, live stream ids and check token information from html source codes;
(4) Acquiring the latest mapping file of the gift id and the name of the live broadcasting room, analyzing and recording the mapping file into a memory;
(5) Simulating a webpage request to interact with a websocket interface of the server by using an aiohttp framework, and analyzing returned data of the server;
(6) And storing the bullet screen information after analysis to a designated position.
2. The interactive method of the live interaction system capable of being configured to automatically drive the virtual anchor according to claim 1, wherein the client is further provided with a user tracking management mechanism, a user use tracking function is added, any user receives and sends messages with a user management server when using the client related function service, the system copies and stores various operation information of the user, and then analysis is performed through an auxiliary analysis tool.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210303776.5A CN114710688B (en) | 2022-03-26 | 2022-03-26 | Live broadcast interaction system and method capable of being configured to automatically drive virtual anchor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210303776.5A CN114710688B (en) | 2022-03-26 | 2022-03-26 | Live broadcast interaction system and method capable of being configured to automatically drive virtual anchor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114710688A CN114710688A (en) | 2022-07-05 |
| CN114710688B true CN114710688B (en) | 2024-03-05 |
Family
ID=82170661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210303776.5A Active CN114710688B (en) | 2022-03-26 | 2022-03-26 | Live broadcast interaction system and method capable of being configured to automatically drive virtual anchor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114710688B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118945383A (en) * | 2023-05-09 | 2024-11-12 | 南京硅基智能科技有限公司 | A group control live broadcast method and device, electronic equipment and storage medium |
| CN116996703A (en) * | 2023-08-23 | 2023-11-03 | 中科智宏(北京)科技有限公司 | Digital live broadcast interaction method, system, equipment and storage medium |
| CN118921534B (en) * | 2024-10-09 | 2025-01-07 | 北京达佳互联信息技术有限公司 | Information display method, device, electronic device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109660818A (en) * | 2018-12-30 | 2019-04-19 | 广东彼雍德云教育科技有限公司 | A kind of virtual interactive live broadcast system |
| US10467792B1 (en) * | 2017-08-24 | 2019-11-05 | Amazon Technologies, Inc. | Simulating communication expressions using virtual objects |
-
2022
- 2022-03-26 CN CN202210303776.5A patent/CN114710688B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10467792B1 (en) * | 2017-08-24 | 2019-11-05 | Amazon Technologies, Inc. | Simulating communication expressions using virtual objects |
| CN109660818A (en) * | 2018-12-30 | 2019-04-19 | 广东彼雍德云教育科技有限公司 | A kind of virtual interactive live broadcast system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114710688A (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114710688B (en) | Live broadcast interaction system and method capable of being configured to automatically drive virtual anchor | |
| US7617272B2 (en) | Systems and methods for enhancing streaming media | |
| US8353406B2 (en) | System, method, and computer readable medium for creating a video clip | |
| CA2600884C (en) | Method and apparatus for editing media | |
| US8286070B2 (en) | Enhanced capture, management and distribution of live presentations | |
| US20020120939A1 (en) | Webcasting system and method | |
| US20020091658A1 (en) | Multimedia electronic education system and method | |
| US20190373208A1 (en) | Remotely accessed virtual recording room | |
| CN106095905B (en) | Internet interactive platform based on PPT playback | |
| KR20120028380A (en) | System for sequential juxtaposition of separately recorded scenes | |
| US20090037801A1 (en) | Method and apparatus for automatic user manual generation | |
| CN102568260A (en) | Video information processing method based on three-split screen courseware recording | |
| CN105554512A (en) | Saas cloud platform applicable to new media content fusion | |
| US11818186B2 (en) | Distributed network recording system with synchronous multi-actor recording | |
| CN111191472A (en) | Teaching auxiliary translation learning system and method | |
| US8223153B2 (en) | Apparatus and method of authoring animation through storyboard | |
| CN118016110B (en) | Media data recording and playing method | |
| CN118695053A (en) | A method, system and related device for driving multimodal AI model live broadcast | |
| Ohnishi et al. | Prototype design of playback and search system for lecture video content using google cloud api | |
| CN116703668A (en) | Railway engineering remote teaching method, device, computer equipment and system | |
| KR20010070867A (en) | Web streaming mechanism and data structure of multimedia contents for on-line presentation, and a system structure for transfer-management in computer networks | |
| CN115866171A (en) | Video playback method and system based on video monitoring platform | |
| CN114285836A (en) | Video playing method, device and medium | |
| JP4585382B2 (en) | Client terminal, management server, usage program, and management program | |
| JP2001320667A (en) | Service providing device and method, reception terminal and method, and service providing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 361000 3F-A317, Zone C, Innovation Building, Software Park, Torch High tech Zone, Xiamen City, Fujian Province Patentee after: Fujian Reliable Cloud Computing Technology Co.,Ltd. Country or region after: China Address before: 361000 3f-a317, Zone C, innovation building, software park, torch hi tech Zone, Huli District, Xiamen City, Fujian Province Patentee before: Xiamen Biebeyun Co.,Ltd. Country or region before: China |